A Cost-Efficient Method for Continuous Top-k Processing over Data Stream

Continuous top-k query over data stream is very important for several on-line applications, including network monitoring, communication, sensor networks and stock market trading, etc. In this paper, we propose an effective pruning technique, which minimizes the number of tuples that need to be stored and manipulated. Based on it, a cost-efficient method for continuous top-k processing over single data stream is proposed, whose computation complex and memory requirements are greatly decreased. The data structure we use is able to support preference function whether it is or not monotonic and the running time is hardly effected by dimensions. Theoretical analysis and experimental evidences show the efficiency of proposed approaches both on storage reduction and performance improvement.